Note: large date ranges can take some time to process on initial search due to the sheer volume of data we have collected. Subsequent searches using the same date range should run quickly due to Elasticsearch caching.
# query start date/time (inclusive)
rangestart <- "2020-01-01 00:00:00"
# query end date/time (exclusive)
rangeend <- "2020-08-01 00:00:00"
# query semantic similarity phrase (choose one of these examples or enter your own)
#semantic_phrase <- "Elementary school students are not coping well with distance learning."
#semantic_phrase <- "How do you stay at home when you are homeless?"
#semantic_phrase <- "My wedding has been postponed due to the coronavirus."
#semantic_phrase <- "I lost my job because of COVID-19. How am I going to be able to make rent?"
#semantic_phrase <- "I am diabetic and out of work because of coronavirus. I am worried I won't be able to get insulin without insurance."
#semantic_phrase <- "There is going to be a COVID-19 baby boom..."
#semantic_phrase <- "Vitamin"
semantic_phrase <- ""
# return results in chronological order or as a random sample within the range
# (ignored if semantic_phrase is not blank)
random_sample <- FALSE
# number of results to return (max 10,000)
resultsize <- 10000
####TEMPORARY SETTINGS####
# number of high level clusters (temporary until automatic selection implemented)
k <- 5
# number of subclusters per high level cluster (temporary until automatic selection implemented)
cluster.k <- 8
# show/hide extra info (temporary until tabs are implemented)
show_original_subcluster_plots <- FALSE
show_regrouped_subcluster_plots <- TRUE
show_word_freqs <- FALSE
show_center_nn <- FALSE## [1] "Subclustering cluster 1 ..."
## [1] "Subclustering cluster 2 ..."
## [1] "Subclustering cluster 3 ..."
## [1] "Subclustering cluster 4 ..."
## [1] "Subclustering cluster 5 ..."## [1] "Plotting cluster 1 ..."
## [1] "Plotting cluster 2 ..."
## [1] "Plotting cluster 3 ..."
## [1] "Plotting cluster 4 ..."
## [1] "Plotting cluster 5 ..."